Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [selected
    -0.08
     Bing
    -0.07
     branches
    -0.07
    mont
    -0.06
    vas
    -0.06
    长
    -0.06
    ご覧
    -0.06
    ше
    -0.06
    vault
    -0.06
    $view
    -0.06
    POSITIVE LOGITS
    0.07
    妳
    0.07
     selectively
    0.07
     админист
    0.07
     shutting
    0.07
    (CancellationToken
    0.06
    	sign
    0.06
    .pag
    0.06
    iforn
    0.06
     współpr
    0.06
    Act Density 0.000%

    No Known Activations